QinyuanCheng's picture

QinyuanCheng

Cqy2019

·

AI & ML interests

None yet

Recent Activity

reacted to AdinaY's post with 🔥 about 19 hours ago

MOSS Transcribe Diarize 🔊 A multimodal model for Speaker-Attributed, Time-Stamped Transcription from OpenMOSS. https://huggingface.co/papers/2601.01554 https://huggingface.co/spaces/OpenMOSS-Team/MOSS-transcribe-diarize ✨ Single-pass end-to-end SATS ✨ 128k context, ~90 min audio ✨ Robust to overlap & noise

liked a model about 20 hours ago

LEMAS-Project/LEMAS-TTS

upvoted a paper 1 day ago

Klear: Unified Multi-Task Audio-Video Joint Generation

View all activity

Organizations

Cqy2019 's models 8

Cqy2019/m1_sft_32B_v2_rft

Text Generation • 33B • Updated Jan 17, 2025 • 4

Cqy2019/m1_sft_72B_v2_rft

Text Generation • 73B • Updated Jan 17, 2025 • 1

Cqy2019/m1_sft_32B_v2

Text Generation • 33B • Updated Jan 17, 2025 • 2

Cqy2019/m1_sft_72B_v2

Text Generation • 73B • Updated Jan 17, 2025 • 1

Cqy2019/m1-32B-sft

Text Generation • 33B • Updated Jan 13, 2025 • 3

Cqy2019/m1-72B-sft

Text Generation • 73B • Updated Jan 13, 2025 • 3

Cqy2019/m1-72B-1m

Text Generation • 73B • Updated Jan 9, 2025 • 1

Cqy2019/m1-32B-1m

Text Generation • 33B • Updated Jan 9, 2025 • 2